文章基本信息

标题：Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification
本地全文：下载
作者：Soumya Chatterjee ; Ayush Maheshwari ; Ganesh Ramakrishnan 等
期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：2829-2841
DOI：10.18653/v1/2021.eacl-main.247
语种：English
出版社：ACL Anthology
摘要：We consider the problem of multi-label classification, where the labels lie on a hierarchy. However, unlike most existing works in hierarchical multi-label classification, we do not assume that the label-hierarchy is known. Encouraged by the recent success of hyperbolic embeddings in capturing hierarchical relations, we propose to jointly learn the classifier parameters as well as the label embeddings. Such a joint learning is expected to provide a twofold advantage: i) the classifier generalises better as it leverages the prior knowledge of existence of a hierarchy over the labels, and ii) in addition to the label co-occurrence information, the label-embedding may benefit from the manifold structure of the input datapoints, leading to embeddings that are more faithful to the label hierarchy. We propose a novel formulation for the joint learning and empirically evaluate its efficacy. The results show that the joint learning improves over the baseline that employs label co-occurrence based pre-trained hyperbolic embeddings. Moreover, the proposed classifiers achieve state-of-the-art generalization on standard benchmarks. We also present evaluation of the hyperbolic embeddings obtained by joint learning and show that they represent the hierarchy more accurately than the other alternatives.